things-mac
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
92
93%
Does it follow best practices?
Impact
96%
3.55xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the target application (Things 3), the mechanism (CLI + URL scheme), specific capabilities (add, update, read, search, list), and explicit trigger conditions. The only minor issue is the reference to 'OpenClaw' which is an unusual name that users might not use, but overall the description is well-crafted and distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: add/update projects+todos via URL scheme, read/search/list from the local Things database. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (manage Things 3 via CLI — add/update projects+todos, read/search/list from database) and when ('Use when a user asks to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'add a task to Things', 'list inbox/today/upcoming', 'search tasks', 'inspect projects/areas/tags', 'Things 3'. The term 'OpenClaw' is unusual but the rest covers natural user language well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific application (Things 3) on a specific platform (macOS) using a specific tool (`things` CLI). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that provides comprehensive CLI reference for Things 3 management. It excels in conciseness and actionability with numerous concrete, executable examples. The main weakness is that multi-step workflows (especially update operations involving search → get ID → dry-run → execute) could benefit from explicit sequencing and validation checkpoints.
Suggestions
Add an explicit numbered workflow for update operations: 1. Search for the item, 2. Note the UUID, 3. Dry-run the update, 4. Execute the update — to make the multi-step process clearer and safer.
Consider recommending --dry-run as a mandatory first step before any write/update operation, especially for --completed/--canceled which are described as 'soft-delete-ish'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude knows what a URL scheme is, what UUIDs are, and how CLI tools work. Every section provides only the information Claude wouldn't already know—specific flags, commands, and setup requirements. No unnecessary explanations. | 3 / 3 |
Actionability | Every section provides concrete, copy-paste-ready commands with real-world examples. The examples cover basic through advanced use cases (add, update, search, checklist items, STDIN input) with specific flags and arguments. The setup section includes exact install commands. | 3 / 3 |
Workflow Clarity | Multi-step workflows like 'search for ID then update' are present but implicit rather than explicitly sequenced. The --dry-run safe preview is mentioned but not enforced as a validation checkpoint before destructive update operations. For update operations that modify/complete/cancel todos, a clearer validate-then-execute workflow with explicit checkpoints would be appropriate. | 2 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into logical sections (Setup, Read-only, Write, Examples: add, Examples: modify, Delete, Notes). The skill is appropriately sized for a single file and doesn't need external references. Sections are clearly labeled and easy to navigate. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.